Commit
•
2cab2ec
1
Parent(s):
cb147ba
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +19 -19
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 263.54 +/- 19.80
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7ba8885fdf30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ba8885fdfc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ba8885fe050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ba8885fe0e0>", "_build": "<function ActorCriticPolicy._build at 0x7ba8885fe170>", "forward": "<function ActorCriticPolicy.forward at 0x7ba8885fe200>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ba8885fe290>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ba8885fe320>", "_predict": "<function ActorCriticPolicy._predict at 0x7ba8885fe3b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ba8885fe440>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ba8885fe4d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ba8885fe560>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ba8885a7f40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718779597026108787, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7e86259c5cf0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e86259c5d80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e86259c5e10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e86259c5ea0>", "_build": "<function ActorCriticPolicy._build at 0x7e86259c5f30>", "forward": "<function ActorCriticPolicy.forward at 0x7e86259c5fc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e86259c6050>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e86259c60e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7e86259c6170>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e86259c6200>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e86259c6290>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e86259c6320>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e8625956d00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 257760, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718799482497551295, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.75424, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 308, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf083983c45c83d53dff87f08b132f6bb3ee6d6c2199d5a5190c930026a4afb5
|
3 |
+
size 148033
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,17 +41,17 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining":
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7e86259c5cf0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e86259c5d80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e86259c5e10>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e86259c5ea0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7e86259c5f30>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7e86259c5fc0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7e86259c6050>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e86259c60e0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7e86259c6170>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e86259c6200>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e86259c6290>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7e86259c6320>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7e8625956d00>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 257760,
|
25 |
"_total_timesteps": 1000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1718799482497551295,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": 0.75424,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 308,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c609b12208268d0962fe2d592f1e97401774f09a735a81141b3b81d4762df0a
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea26e5bf53ea5d92ae8b20211afabf7ea0c917c73467dc99f437fe931e03c2fc
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 263.53918409999994, "std_reward": 19.797638871954415, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-19T12:24:40.872061"}
|